Daochen Zha
Daochen Zha
We are brainstorming how we could develop smaller versions of the large games while capturing the key features of the game. For example, Majong is too complex since it is...
你好， 我们只提供训练环境和基础算法，以方便测试。实际应用还需要很多工程的东西。比如把state和action和真实游戏中对接起来。state和action都是numpy向量，可以参考https://github.com/datamllab/rlcard/blob/master/rlcard/envs/doudizhu.py 实际应用中可能还需要其他的一些工程性的东西来提高效果。比如调整reward，以及尝试不同的特征。我们的目标是提供最基本框架和和基本的算法，方便后续开发。谢谢。
@ArshartCloud You are right. The state features are usually very important in training agents. The wrapper here is just an example, which is not necessarily the best. You can customize...
@jkterry1 Hey, congratulations to your achievements. This is a good idea to have versioning. I will work on this and add the old version back.
Yes, we will include versioning from now on. Just trying to make sure, do you guys want to add the old version of doudizhu back?
Sure. We will add versioning.
@diegop2211 Thanks for the feedback. Currently, we already support various betting amounts in Texas Hold'em. Could you elaborate more on what you proposed?
@AhmedKhaled945 Thanks for your interest! Unfortunately, we have not developed a rule-based agent for Mahjong yet. We do have every rule agents for other games in https://github.com/datamllab/rlcard/tree/master/rlcard/models
@aetheryang The id here is just an ID to make the selection easier. It does not correspond to the action in the environment.
@alexx-ftw Yes I will close it. Thanks!